When I see a paper on explainability, first question I
ask is: "What does it explain?", the data-fitting strategy of
the fitter? or real-life events such as death or survival.
I believe this paper arxiv.org/pdf/2010.10596…
is mostly about the former, as can be seen from the 1/
ask is: "What does it explain?", the data-fitting strategy of
the fitter? or real-life events such as death or survival.
I believe this paper arxiv.org/pdf/2010.10596…
is mostly about the former, as can be seen from the 1/
equations and from the absence of any world-model.
While it is sometimes useful to explain the data-fitting system (eg. for debugging), it is also important to distinguish this kind of counterfactual explanations
from the kind generated in the causal inference literature.
2/3
While it is sometimes useful to explain the data-fitting system (eg. for debugging), it is also important to distinguish this kind of counterfactual explanations
from the kind generated in the causal inference literature.
2/3
Beware, a model-blind system might conclude that
the rooster crow explains the sunrise. It might also explain that your loan was denied because you are a male, and would also have been denied if you were a female. I wonder how ML folks would debug this system.
the rooster crow explains the sunrise. It might also explain that your loan was denied because you are a male, and would also have been denied if you were a female. I wonder how ML folks would debug this system.
Beware, a model-blind system might conclude that
the rooster crow explains the sunrise.
the rooster crow explains the sunrise.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
